Scrapping civilian casualty incidents from Airwars

___________________________________________________________________________

Computing Resources:

This project was created on a lenovo legion 7i laptop with a i9-14900HX chip, 64gb of DDR5 RAM, and an Nvidia RTX-4070 GPU with 8gb of GDDR6. The operating system initially used was Ubuntu 24.10. However, when we attempted to configure our GPU to process text data for the language model we learned that this version of Ubuntu contains the newest kernel which updates nvidia-cli and cuda drivers that are not compatible with tensorflow or pytorch needed for the text package. We moved to Ubuntu 24.04 LTS within WSL2 on Windows 11 and we were able to configure the GPU. Given that Airwars also goes back and corrects archived incidents, it is easier to just run the full process on all available incident records when needed, and the GPU cuts back on the processing time. Modeling data on a GPU for the language model cut the process time from 2.5 hours to about 20 minutes.

We use r-base 4.4.1 from anaconda and rstudio 2024.04.02. We have also used these same packages on rstudio-server via WSL2 but prefer to isolate the computing environment.

We store all of our data in a SQLite database that can also be found in our github repository

Structure of SQlite database

The scrapped data resulted in over 800 unique events stored in two tables in a SQLite database.

Table 1 contains incident metadata (e.g., unique id, incident date, web-page URL).
Table 2 stores the specific incident information such as the number of deaths, breakdown of deaths (children, adults), type of attack, and cause of death, incident coordinates and results from Nominatim, and sentiment scores for seven emotional states.
Table 3 contains the Hamas Ministry of Health (MoH) daily casualties.
The first two tables relate to each other through the unique incident identification numbers provided by Airwars. We relate the MoH table with the Airwars tables by aggregating up to the date.

# connect to database
mydb <- dbConnect(
  RSQLite::SQLite(), 
  "~/repos/airwars_scraping_project/database/airwars_db.sqlite")

dbListTables(mydb) # print tables in database

[1] "airwars_incidents" "airwars_meta"      "daily_casualties"

Scraping Airwars Civilian Casualty Incidents

The image below is an example of the Airwars incident metadata that are presented as baseball cards. This information is presented in one web-page and we start our workflow at this junction. We read the main website in Airwars that houses this information and only scrape Incident Date and Incident ID to build specific incident web-URLs that we later scrape for content.
- All of the code to conduct the scraping and processing of these data are found in our github page under code/scrape_process_incidence, which this code has been optimized and takes about 30 minutes on our laptop (32gb of RAM is sufficient) with a fast internet connection.
- Here we only explain how we pre-processed the data as it related to preparing for analysis.
- For a lot of the scraping we used selectorgadget to get the xpath and pass it through the Rvest package.

Metadata table: We scrape the main Airwars website parse information we need to build a table containing each incident’s web-url (over 800 URLs), as seen in the example below.

# read in data tables
airwars_meta <- tbl(mydb, "airwars_meta") |> 
  as_tibble() |> 
  # convert Incident_Date to date format
  mutate(Incident_Date = as_date(Incident_Date)) |> 
  arrange(Incident_Date)

airwars_meta |> head() |> kable()

Incident_Date	Incident_id	link
2023-10-07	ispt0019a	https://airwars.org/civilian-casualties/ispt0019a-october-7-2023/
2023-10-07	ispt0019	https://airwars.org/civilian-casualties/ispt0019-october-7-2023/
2023-10-07	ispt0017	https://airwars.org/civilian-casualties/ispt0017-october-7-2023/
2023-10-07	ispt0011	https://airwars.org/civilian-casualties/ispt0011-october-7-2023/
2023-10-07	ispt0010	https://airwars.org/civilian-casualties/ispt0010-october-7-2023/
2023-10-07	ispt0003	https://airwars.org/civilian-casualties/ispt0003-october-7-2023/

Using the web-urls we built in the metadata table, we loop through them and scrape each URL (see below for example) to parse incident assessments as seen below.
- Each incident contains an assessment section detailing what transpired during the incident, whom was known to be involved and the victims it produced. We will use this text to get emotional scores later.

Incidence table: Our final table contains the fields that Airwars populates for each incident. Besides parsing this information we also had to process the data, specifically, there are fields that contain ranges of kills (i.e., 3-5) or counts (i.e., 1 child, 3 women, 1 man) which we had to strip these strings into their own columns. This allows us to estimate how many children and women have been reported as civilian casualties. Our data contains 24 variables with 804 incidents reported by Airwars.

airwars_incidents <- tbl(mydb, "airwars_incidents") |> 
  as_tibble() 

airwars_incidents |> 
  head() |> 
  select(-assessment:-surprise) |> 
  kable()

Incident_id	Strike status	Strike type	Civilian infrastructure	Civilian harm reported	Civilians reported killed	Civilians reported injured	Cause of injury / death	Airwars civilian harm grading	Impact	Suspected belligerent	min_killed	max_killed	casualty_estimate	killed	location_meta	incident_lat	incident_long	target_type	target_address_type	lat_min	lat_max	long_min	long_max	Suspected belligerents	Known belligerent	Suspected target	Known target	Causes of injury / death	children_killed	women_killed	men_killed	Civilian_type
ispt0001	Single source claim	Airstrike and/or Artillery	Healthcare facility	Yes	1	2	Heavy weapons and explosive munitions	Fair	Healthcare	Israeli Military	1	1	absolute	1	Rafah the Gaza Strip	31.296628	34.244689	tertiary	road	31.29471	31.29727	34.24404	34.24777	NA	NA	NA	NA	NA	NA	NA	1	(1 man1 healthcare_personnel)
ispt00012	Likely strike	Airstrike	Healthcare facility	Yes	1	4	Heavy weapons and explosive munitions	Fair	Healthcare	Israeli Military	1	1	absolute	1	Nasser medical complex Khan Younis the Gaza Strip	31.347002	34.292327	hospital	amenity	31.34554	31.34852	34.29053	34.29406	NA	NA	NA	NA	NA	NA	NA	1	(1 man1 healthcare_personnel)
ispt00013	Likely strike	Airstrike	Healthcare facility	Yes	Unknown	5	Heavy weapons and explosive munitions	Fair	Healthcare	Israeli Military	NA	NA	NA	NA	Nasser medical complex Khan Younis the Gaza Strip	31.347153	34.292774	hospital	amenity	31.34554	31.34852	34.29053	34.29406	NA	NA	NA	NA	NA	NA	NA	NA	NA
ispt0002	Likely strike	Airstrike	Residential building	Yes	3 – 7	4	Heavy weapons and explosive munitions	Fair	NA	Israeli Military	3	7	range	5	Khuza a Khan Younis the Gaza Strip	31.522567	34.462869	tertiary	road	31.52175	31.53208	34.46157	34.47451	NA	NA	NA	NA	NA	2	3	1	(2 children3 women1 man)
ispt0003	Likely strike	Airstrike	NA	Yes	1	3	Heavy weapons and explosive munitions	Fair	NA	Israeli Military	1	1	absolute	1	Al Baraa Mosque Gaza the Gaza Strip	31.501846	34.437058	place_of_worship	amenity	31.50165	31.50191	34.43679	34.43723	NA	NA	NA	NA	NA	NA	NA	1	(1 man)
ispt0004	Likely strike	Airstrike	Residential building	Yes	15	NA	Heavy weapons and explosive munitions	Fair	NA	Israeli Military	15	15	absolute	15	home of the Al Dous family in Al Zaytoun neighborhood south of Gaza City Gaza the Gaza Strip	31.485479	34.444885	residential	road	31.48442	31.48662	34.44390	34.44632	NA	NA	NA	NA	NA	7	3	5	(7 children3 women5 men)

MoH Daily Casualties

Palestine Dataset published daily Gaza casualty counts that they take from the Hamas MoH; however, they do not make a distinction whether a casualty was a civilian or militant so their numbers should be higher than what we derive from Airwars.¹

We use the Palestine API https://data.techforpalestine.org/api/v2/casualties_daily.json and parse the JSON to save into our database after a little bit of data wrangling.

tbl(mydb, "daily_casualties") |> 
  as_tibble() |> 
  mutate(Incident_Date = lubridate::as_date(Incident_Date)) |> 
  head() |> 
  kable()

Incident_Date	name	value
2023-10-07	Children	0
2023-10-07	Women	0
2023-10-07	Total	232
2023-10-08	Children	78
2023-10-08	Women	41
2023-10-08	Total	370

Enriching Data with Reverse geocoding

Airwars when possible includes location coordinates of where the incident took place. Although this information is contained within the assessment, Airwars standardizes it’s location with a heading under “Geolocation notes” which we were able to parse the latitude and longitude to use for geographic plotting. Of the 804 Incidents about 65% contain geographic coordinates.

We used the Nominatim open street map API to reverse geocode our coordinates and bring back the type of location that was the location target for incidents that contained coordinates. We also save out a boundary box set of coordinates.

airwars_incidents |> 
  select(target_type, contains("lat"), contains("long")) |> 
  head() |> 
  kable()

target_type	incident_lat	lat_min	lat_max	incident_long	long_min	long_max
tertiary	31.296628	31.29471	31.29727	34.244689	34.24404	34.24777
hospital	31.347002	31.34554	31.34852	34.292327	34.29053	34.29406
hospital	31.347153	31.34554	31.34852	34.292774	34.29053	34.29406
tertiary	31.522567	31.52175	31.53208	34.462869	34.46157	34.47451
place_of_worship	31.501846	31.50165	31.50191	34.437058	34.43679	34.43723
residential	31.485479	31.48442	31.48662	34.444885	34.44390	34.44632

Sentiment Analysis

After attempting several text classification models and some question/context model we landed onj-hartmann/emotion-english-distilroberta-base because it goes beyond just a positive/negative evaluation but analysis text for Ekman’s 6 basic emotions that is common in psychological work on emotions.Moreover, this model affords us the ability to examine the emotion tone over time for these assessments.²
- We get scores for each emotions, the closer to one the stronger the association, while all the scores add up to 1.
- The model is trained on a balanced subset from the datasets listed above (2,811 observations per emotion, i.e., nearly 20k observations in total). 80% of this balanced subset is used for training and 20% for evaluation. The evaluation accuracy is 66% (vs. the random-chance baseline of 1/7 = 14%).
- Given that we have over 800 assessments we decided to use text ³ while it allows us the ability to use a laptop GPU (GTX 4070)⁴ to process these models for each incident. This resulted in large processing gains.
- Below we print an example of these scores while we truncate the assessment text.

airwars_incidents |> 
  slice_sample(n=1) |> 
  select(assessment:surprise) |> 
  mutate(assessment = str_trunc(assessment, 200),
         across(where(is.double), ~ round(.x, 2))) |> 
  kable()

assessment	anger	disgust	fear	joy	neutral	sadness	surprise
Shortly before 6pm on Sunday, 29th October 2023, at least 35 civilians, including at least eight women and 16 children, were reportedly killed and dozens were injured in an alleged Israeli airstrik…	0.02	0	0.2	0	0.01	0.74	0.01

Footnotes

Note. Confidence is low to moderate since the data comes from the Hamas MoH.↩︎
- The model is trained on a balanced subset from the datasets listed above (2,811 observations per emotion, i.e., nearly 20k observations in total). 80% of this balanced subset is used for training and 20% for evaluation. The evaluation accuracy is 66% (vs. the random-chance baseline of 1/7 = 14%).
↩︎
An R-package for analyzing natural language with transformers from HuggingFace using Natural Language Processing and Machine Learning.↩︎
The installation for Text is tricky as the right python libraries must be installed. To compile models with the GPU, we learned that nvidia cuda drivers must be installed for version 12.1. Additionally, we could only get this to work via anaconda within Ubuntu 24.04 installed through WSL2 on Windows 11. Ubuntu 24.10 comes with a kernal that forces cuda 12.8 to be installed and did not work for us in a dual boot system.↩︎